AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Graph convolutional networks for learning with few clean and many noisy labels

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum, Cordelia Schmid

ECCV 2020 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GCN-based cleaning of noisy examples to class prototypesClass prototypes · Low-shot ImageNet (1-shot)top-5 accuracy: 45.3 -> 67.8Improved
add GCN-based cleaning of noisy examples to class prototypesClass prototypes · Low-shot ImageNet (20-shot)top-5 accuracy: 77.8 -> 78.2No clear effect
add noisy examples with unit relevance (beta=1) instead of cleaning (ablation)Class prototypes · Low-shot ImageNet (20-shot)top-5 accuracy: 77.8 -> 58.7Hurt
add graph propagation (GCN instead of MLP) (ablation)relevance predictor · Low-shot ImageNet (1-shot)top-5 accuracy: 63.6 -> 67.8Improved
add graph propagation (GCN instead of MLP) (ablation)relevance predictor · Low-shot ImageNet (5-shot)top-5 accuracy: 73.7 -> 73.9No clear effect
add learned GCN instead of label propagation (ablation)relevance predictor · Low-shot ImageNet (1-shot)top-5 accuracy: 62.6 -> 67.8Improved
replace class prototypes with cosine classifier learning (ablation)GCN-cleaned data, ResNet-10 · Low-shot ImageNet (1-shot)top-5 accuracy: 67.8 -> 73.2Improved
add deep network fine-tuning on top of cosine classifier (ablation)GCN-cleaned data, ResNet-50 · Low-shot ImageNet (1-shot)top-5 accuracy: 78.0 -> 80.2Improved
weight noisy examples by relevance instead of beta=1 (ablation)Class prototypes · Low-shot ImageNet (1-shot)top-5 accuracy: 56.1 -> 67.8Improved
add graph propagation (GCN instead of MLP) (ablation)relevance predictor · Low-shot Places365 (1-shot)top-5 accuracy: 46.9 -> 47.1No clear effect
add noisy examples with unit relevance (beta=1) (ablation)Class prototypes · Low-shot Places365 (20-shot)top-5 accuracy: 62.3 -> 50.8Hurt
add GCN cleaning of noisy data to prototypesClass prototypes · Mini-ImageNet 5-way 5-shotaccuracy: 71.2 -> 74.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy